• Publications
  • Influence
Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision
TLDR
We propose to improve the effectiveness of a neural aspect and opinion term extraction model by training it with not only the human labeled data but also the rule labeled auxiliary data. Expand
  • 15
  • 4
  • PDF
Incorporating Context and External Knowledge for Pronoun Coreference Resolution
TLDR
We propose a two-layer model for pronoun coreference resolution that leverages both context and external knowledge, where a knowledge attention mechanism is designed to ensure the model leveraging the appropriate source of external knowledge based on different context. Expand
  • 15
  • 4
  • PDF
Multilingual and Multi-Aspect Hate Speech Analysis
TLDR
We present a new multilingual multi-aspect hate speech analysis dataset and use it to test the current state-of-the-art multilingual multitask learning approaches. Expand
  • 21
  • 2
  • PDF
Overview of UI-CCG Systems for Event Argument Extraction , Entity Discovery and Linking , and Slot Filler Validation
In this paper, we describe the University of Illinois (UI CCG) submission to the 2013 TAC KBP Event Argument Extraction (EAE), English Entity Discovery and Linking (EDL), and Slot Filler ValidationExpand
  • 18
  • 2
  • PDF
ASER: A Large-scale Eventuality Knowledge Graph
TLDR
We develop ASER (activities, states, events, and their relations), a large-scale eventuality knowledge graph extracted from 11-billion-token unstructured textual data. Expand
  • 12
  • 2
  • PDF
TransOMCS: From Linguistic Graphs to Commonsense Knowledge
TLDR
In this paper, we explore a practical way of mining commonsense knowledge from linguistic graphs, with the goal of transferring cheap knowledge obtained with linguistic patterns into expensive Commonsense knowledge. Expand
  • 6
  • 2
  • PDF
Knowledge-aware Pronoun Coreference Resolution
TLDR
We propose a novel end-toend model that learns to resolve pronoun coreference with general knowledge graphs, which outperforms state-of-the-art baselines by a large margin. Expand
  • 9
  • 1
  • PDF
SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition
TLDR
We introduce SP-10K, a large-scale evaluation set that provides human ratings for the plausibility of 10,000 SP pairs over five SP relations, covering 2,500 most frequent verbs, nouns, and adjectives in American English. Expand
  • 8
  • 1
  • PDF
What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues
TLDR
We formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate how the visual information can help resolve pronouns in dialogues. Expand
  • 5
  • 1
  • PDF
Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks
TLDR
We design an event meta-schema to characterize the semantic relatedness of social events and build an event-based heterogeneous information network integrating information from external knowledge base, and propose a novel Pair-wise Popularity Graph Convolutional Network (PP-GCN) based fine-grained social event categorization model. Expand
  • 16
  • PDF